Send an intercept event to the Gateplex API. Use this every time an AI agent performs an action that should be logged, governed, or audited.
| Name | Required | Description | Default |
|---|---|---|---|
| input | No | Raw input/prompt | |
| model | No | Model identifier, e.g. 'gpt-4o' | |
| output | No | Raw output | |
| flagged | No | ||
| agent_id | No | UUID of the agent generating this intercept | |
| metadata | No | ||
| event_type | Yes | Event type, e.g. 'llm_call', 'tool_call', 'http_request' | |
| latency_ms | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It only says 'send an intercept event' but does not mention side effects, persistence, authentication, error behavior, or consequences of calling this tool. This is a significant transparency gap for a remote API call.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with the verb and resource. Every word earns its place; no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For an 8-parameter tool with nested objects and no output schema/annotations, the description is too minimal. It does not explain return values, errors, or usage nuances. The description is incomplete for an agent trying to invoke this tool correctly in varied situations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is moderate (63%). The description adds no extra meaning to parameters; it does not clarify `flagged`, `latency_ms`, or `metadata`. The schema descriptions for many parameters are adequate, so baseline 3 applies, but the description does not compensate for undocumented parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific action ('Send an intercept event') and destination ('to the Gateplex API'), clearly distinguishing it from sibling tools (check_guardrails, get_feed). It conveys the resource and operation unambiguously.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit usage context: 'Use this every time an AI agent performs an action that should be logged, governed, or audited.' This gives clear when-to-use guidance, though it does not mention when-not-to-use or alternative tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a distinct purpose: checking rules, fetching logs, and sending events. No overlap or ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case: check_guardrails, get_feed, log_intercept.
Three tools is well-scoped for the server's focused domain of guardrail enforcement and audit logging.
The surface covers the full workflow: check rules before acting, log the action, and retrieve the feed later. No obvious gaps for this domain.
